All authors
Claude Skills by williamblair333
github.com/williamblair33353 skills3 installs68 views
- Plans> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking. **Goal:** Build and promote the `pre-mortem` skill — a forward-looking adversarial failure analysis that fires on every consequential action, producing a visible checklist with adversarial+steelman findings, severity-tiered escalation, and MemPalace audit logging. **Archite...Votes: 0GitHub stars: 3
- Dream SynthesizerAnalyze Claude Code session traces and extract recurring mistakes and proven playbooks for future sessionsVotes: 0GitHub stars: 3
- Gemini Auto SkillMonitors Gemini CLI sessions for reusable workflows and drafts native Gemini skills.Votes: 0GitHub stars: 3
- Agent Harness Backend Adoption EvalEvaluate a proposed library or backend as a replacement for an existing one. Produces a structured assessment: architecture comparison, benchmark credibility, unproven risks, creative angles, and a staged recommendation. Use when a new library surfaces as a candidate to replace an embedded dependency (vector DB, cache, queue, etc.).Votes: 0GitHub stars: 3
- Agent Harness Competitive AnalysisStructured competitive analysis of an AI agent harness or framework — maps the product against direct/indirect competitors, produces a comparison table, and identifies uncontested advantagesVotes: 0GitHub stars: 3
- Audit Pipeline Fabrication RiskSystematically audit an AI pipeline for hallucination/fabrication propagation paths — where model-generated content (especially URLs, issue numbers, citations) can reach persistent stores without verification. Use when another agent has identified a fabrication risk but you need code-grounded verification before building fixes.Votes: 0GitHub stars: 3
- Auto Maintain Commit And DeployUse when a cron-based auto-maintenance script commits new skills or plugins to git but the install script still has a hardcoded list that needs manual updating, or when new artifacts are committed but not immediately deployed (symlinked, copied, activated). Covers replacing hardcoded artifact lists with dynamic directory scanning and coupling git commits with immediate deployment steps.Votes: 0GitHub stars: 3
- Catch Up PullUse when returning to a repo after time away, when git status reports "up to date" but commits may have landed upstream, or when you need to safely absorb a large batch of upstream changes without losing local work.Votes: 0GitHub stars: 3
- Community Pr Stakeholder ResponseUse when tagged as a stakeholder on an open-source PR or issue comment, especially when the PR has evolved since your last review, involves architectural changes, or requests sign-off on a change touching shared dependencies or parallel work.Votes: 0GitHub stars: 3
- Deep Repo AnalysisFull codebase health audit using jcodemunch — cycles, complexity, coupling, dead code, test gaps, and architectural debt. Use when you need a scored health report with prioritized action items.Votes: 0GitHub stars: 3
- First Run GateUse before calling any project done, before opening a PR that changes runtime behavior, and when setup or install is suspected broken — "does this still work on a clean machine", "did we break install", "why did the gate block my PR". Also use when a gate report comes back failed or blocked and the failure needs reading.Votes: 0GitHub stars: 3
- Fog Of Chess Engine Mode ImplementationImplement a new engineMode variant end-to-end in Fog of Chess — types, UCI bridge, adapter, server polling, REST endpoint, and UI panel — following the validator mode pattern.Votes: 0GitHub stars: 3
- Freecad Parametric Toolkit BuildBuild a FreeCAD parametric CAD toolkit tier by tier — probe APIs first, implement modules, run tests with freecadcmd, fix stdout capture issues.Votes: 0GitHub stars: 3
- GttpUse when the user proposes a specific material, product, hack, or design for a physical, home, or purchase problem and asks whether it works ("what if I…", "analyze this", "is X a good idea", "can I use X instead"); when choosing or buying for a physical, home, or purchase goal ("cheapest/best way to", "should I switch"); when the obvious or purpose-made part, tool, method, API, or library is unavailable, discontinued, or ruled out and the goal has to be reached another way, in any domain inc...Votes: 0GitHub stars: 3
- Healthcheck Interactive HintsUse when a shell healthcheck script uses hint() functions to point users at fix commands, and those commands silently fail or require a separate manual step, or when you want users to be prompted to run the fix immediately after a failure is reported.Votes: 0GitHub stars: 3
- Install Script Cp To SymlinkUse when a bash install script silently skips steps due to `cp` failing on pre-existing symlinks, or when converting copy-based installs to symlink-based for auto-propagation after `git pull`.Votes: 0GitHub stars: 3
- JudgeBefore any Edit or Write lands, spawn an independent code-reviewer subagent that cross-checks the proposed change against structural evidence from jcodemunch (blast radius, changed symbols, untested symbols, PR risk) and serena (references). Catches hallucinated functions, wrong signatures, missed callers, and risky refactors before commit. Triggers when you're about to Edit or Write a non-trivial code change, or when the user asks you to verify/validate/double-check.Votes: 0GitHub stars: 3
- Library Backend Adoption EvalStructured evaluation of a new library as a potential backend replacement. Use when considering migrating from one backend (DB, index, vector store, cache) to another — covers architecture fit, performance claims, risks, creative experiments, and recommendation.Votes: 0GitHub stars: 3
- Mcp Index Empty DiagnosisDiagnose and fix an MCP retrieval tool (jdocmunch, jcodemunch, jdatamunch) that is registered and running but silently returns empty results due to an unpopulated index. Also wires in preventive measures so the gap can't recur silently.Votes: 0GitHub stars: 3
- Milestone Tier ImplementationImplement one or more new library tiers in a milestone-based Python project — read handoff, match existing patterns, implement, wire up, test, then update all docs atomically.Votes: 0GitHub stars: 3
- Occams RazorUse when diagnosing a bug/failure or choosing between competing explanations, hypotheses, or root causes — especially when an exotic, elaborate, or "interesting" cause is tempting. Triggers on "why is this happening", "what's the root cause", intermittent/nondeterministic failures, and any moment you're about to commit to a multi-assumption theory.Votes: 0GitHub stars: 3
- OrchestratorDecompose a PRD or task into a structured JSON task manifest of parallelizable subtasks for multi-agent executionVotes: 0GitHub stars: 3
- OutcomesRubric-aware grader agent — evaluates working agent output against a rubric in a fresh context and produces a structured gap reportVotes: 0GitHub stars: 3
- Per Task Review CycleImplement → spec review → quality review → targeted fix → re-review cycle for multi-task subagent development. Use when executing an implementation plan where each task needs independent verification before moving to the next.Votes: 0GitHub stars: 3
- Platform Removal CleanupUse when dropping support for a platform (OS, runtime, environment) and need to scrub all artifacts: scripts, binaries, docs, template placeholders, config comments, and source code branches.Votes: 0GitHub stars: 3
- Polling Bot Age Filter FixApply a stale-message age gate to a Python Telegram polling bot to prevent a message backlog from exhausting the hourly rate-limit budget. Use after polling-bot-backlog-diagnosis confirms MAX_AGE_SECONDS is missing.Votes: 0GitHub stars: 3
- Polling Bot Backlog DiagnosisDiagnose and fix message backlog and notification-spam issues in cron-based polling bots — covers per-run deduplication flags and stale-message age filtersVotes: 0GitHub stars: 3
- Polling Bot Offset Freeze DiagnosisDiagnose and fix a frozen getUpdates offset in a cron-based Telegram (or similar long-poll) bot caused by two pollers consuming the same bot token. Use when a polling bot suddenly floods old messages, the update offset hasn't advanced for days, or more than one scheduled job calls getUpdates against one token.Votes: 0GitHub stars: 3
- Post Audit Memory CaptureAfter any adversarial/red-team analysis of a component, skill, or control mechanism, write two durable memory notes — design invariants + audit baseline, and closed attack vectors — into the memweave corpus so future sessions can answer "is this change a regression?" without relying on git history alone.Votes: 0GitHub stars: 3
- Post Upgrade Mcp IntegrationAfter any MCP stack upgrade, systematically discover new tools and integrate them into CLAUDE.md routing rules without being askedVotes: 0GitHub stars: 3
- Pre MortemAdversarial failure analysis across 12 dimensions before any consequential action — hooks, scripts, crons, config changes, deployments, gh pr create, git push. Blocks on HIGH/CATASTROPHIC until addressed.Votes: 0GitHub stars: 3
- Prior Art Checkmemweave memory search before any non-trivial task — "have we solved this before?" Fires before any coding, design, or architecture work; runs before the first substantive retrieval tool call.Votes: 0GitHub stars: 3
- Product BriefUse when starting a new project, or when an existing project has no PRODUCT.md — before writing code, choosing a stack, or planning features. Also use when the first-run gate reports a missing or unparseable brief, or when a project cannot say in one sentence who it is for.Votes: 0GitHub stars: 3
- Product Focus ReviewUse when planning, scoping, or reviewing software someone else will use — a v1 plan, a feature request, a "just add these flags" ask, a launch checklist, a README, or a CLI/tool design — especially under deadline pressure or when features are being approved because they are cheap.Votes: 0GitHub stars: 3
- Reading Screenshot DocumentsUse when a .odt/.docx/.pptx or PDF yields no text on extraction because its content is embedded screenshots, when recovering quiz or exam questions from LMS screen captures, or when building a reference from photographed book pages. Symptoms — text extraction returns zero paragraphs, content is only in Pictures/ or media/, dropdowns or menus obscure part of the page.Votes: 0GitHub stars: 3
- Readme SyncAudit a README against actual repo contents, identify undocumented features, and make targeted edits to bring docs in sync with what's actually installed/shipped.Votes: 0GitHub stars: 3
- Review Queue TriageAudit _review/ items, classify by completion signals (status: resolved, REPO-ASSESSMENT + landing commit), auto-move resolved items to _reviewed/, leave uncertain items for user decision.Votes: 0GitHub stars: 3
- Session End ChecklistSession wrap-up checklist — updates CHANGELOG, HANDOFF, considers ROADMAP/README, then commits. Invoke at session end or when the pre-commit hook blocks on missing docs.Votes: 0GitHub stars: 3
- Session Status BriefingProduce a comprehensive session-start status report combining git state, HANDOFF, code health metrics, risk surface, dead code candidates, and retrieval-stack health. Invoke at the start of any session to orient quickly without re-reading files.Votes: 0GitHub stars: 3
- Smart ReviewAuto-classifying code review router — rules floor + shadow classifier → dispatches code-review (low/medium/high) or adversarial-review (critical). Logs every classification to a local drift-audit file.Votes: 0GitHub stars: 3
- Stack Not At Head RemediationRemediate a HEALTHCHECK fail on stack-not-at-head — upgrade uv packages, re-index, pin embedding canary, run post-upgrade integration, update docs, commit, snapshot. Triggers whenever /health reports stack-not-at-head.Votes: 0GitHub stars: 3
- Stale Lock DiagnosisDiagnose and fix stale lock directories blocking background automation scripts (mine, index, sync jobs). Use when hooks are wired but silently not firing, or when a recurring job stopped producing output without any error.Votes: 0GitHub stars: 3
- Stale Pending Memory GuardBefore reporting any memory hit containing "pending/awaiting/needs/consider" as current fact, verify it against the actual source. Prevents propagating resolved items that memory hasn't caught up to.Votes: 0GitHub stars: 3
- Stop Hook Dedup GuardUse when a Claude Code Stop hook sends a Telegram (or other) notification and the same message arrives duplicated at nearly the same timestamp. Symptom is two identical "⏳ Running…" + message pairs appearing within seconds of each other after closing Claude Code.Votes: 0GitHub stars: 3
- Telegram Chat History PersistenceDesign and implement context continuity for a Telegram → Claude gateway. Use when the bot loses cross-session context or when choosing between transcript injection, SQLite buffering, RAG, and the memweave corpus for chat history.Votes: 0GitHub stars: 3
- Telegram Gateway Security AuditDiagnose and harden a Telegram → Claude CLI gateway: fix update_id deduplication failures that spawn duplicate sessions, and inject a disclosure-restriction system prompt so the bot never leaks OS/infra details over the channel.Votes: 0GitHub stars: 3
- Telegram Inline Button PromoteWire up a Telegram inline keyboard button in a polling bot — add button to outbound notification, subscribe to callback_query updates, answer the callback, and collapse a multi-step confirm flow into a single button press.Votes: 0GitHub stars: 3
- Terse ReplyEdit the most recent draft reply to strip verbosity. Use when the user invokes this skill or says "cut the bullshit", "tighten this", "too verbose", or similar.Votes: 0GitHub stars: 3
- Token Economy Prompt AuthoringCraft a minimal, effective system prompt to constrain Claude verbosity in plain web sessions (no harness tooling). Use when you need to paste a behavioral contract into a new Claude.ai conversation or share one for a context where superpowers/skills aren't available.Votes: 0GitHub stars: 3
- Ux HeuristicsEvaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "users are confused", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "is this easy to use". Also trigger when reviewing a design for usability issues, improving form-completion rates, or evaluating information architecture and navigation. Covers Krug''s laws, Nielsen''s 10 heuristics, severity ratings, dark-pattern recognition, and access...Votes: 0GitHub stars: 3